Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44096
    Prev
    Next
    INDEX
    Explanations

    references to historical periods or eras, particularly those designated as "late" or "early."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONGO
    -0.08
    ãĥ©ãĥ³ãĤ¹
    -0.08
    ัà¸Ļà¸Ļ
    -0.07
    redicate
    -0.07
    obus
    -0.07
    ortal
    -0.07
    ampo
    -0.07
    noise
    -0.07
     GetEnumerator
    -0.07
    motor
    -0.07
    POSITIVE LOGITS
     nineteenth
    0.13
    180
    0.13
    -n
    0.11
     Victorian
    0.11
     ninete
    0.09
    -V
    0.09
     vict
    0.09
    19
    0.09
    170
    0.08
    18
    0.08
    Activations Density 0.012%

    No Known Activations